Publications by authors named "Chucheng Chen"
Vision computer-aided diagnostic methods have been used in early ophthalmic disease screening and diagnosis. However, the limited output formats of these methods lead to poor human-computer interaction and low clinical applicability value. Thus, ophthalmic visual question answering is worth studying.
View Article and Find Full Text PDFArticle Synopsis
- * It introduces a multi-modal knowledge graph based on real-world ophthalmology data, which supports a diagnostic model using a contrastive graph attention network (CGAT-ADM) for better patient diagnosis.
- * Results show that this system improves AI services in healthcare, aiding in diagnosis assistance and allowing for deeper insights into patient cases and disease patterns.
Article Synopsis
- Accurate segmentation and quantification of retinal fluid in Optical Coherence Tomography (OCT) images are vital for diagnosing and treating eye diseases like age-related macular degeneration, but achieving this is complicated by variations in fluid characteristics.
- To tackle these challenges, a new multi-scale feature fusion attention network called FNeXter is proposed, which combines ConvNeXt and Transformer models to improve OCT fluid segmentation by capturing both local and long-range features.
- Comprehensive experiments show that FNeXter outperforms existing state-of-the-art methods in effectively segmenting retinal fluid, highlighting its strong performance and potential for clinical applications.